CN107192898B - Audible noise probability prediction method and system for direct current transmission line - Google Patents
Audible noise probability prediction method and system for direct current transmission line Download PDFInfo
- Publication number
- CN107192898B CN107192898B CN201710379112.6A CN201710379112A CN107192898B CN 107192898 B CN107192898 B CN 107192898B CN 201710379112 A CN201710379112 A CN 201710379112A CN 107192898 B CN107192898 B CN 107192898B
- Authority
- CN
- China
- Prior art keywords
- audible noise
- neural network
- artificial neural
- data
- values
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/26—Measuring noise figure; Measuring signal-to-noise ratio
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for predicting audible noise probability of a direct current transmission line, wherein the method comprises the following steps: s1, training the artificial neural network model by using multiple groups of training data, wherein in the training process, the line parameters are used as input data, and the audible noise measurement value is used as output data; s2, inputting the circuit parameters in the multiple groups of training data into the trained artificial neural network model again, and correspondingly obtaining multiple groups of audible noise predicted values; s3, calculating error values of a plurality of groups of corresponding artificial neural network models according to the plurality of groups of audible noise measured values and the plurality of groups of audible noise predicted values; s4, dividing the multiple groups of audible noise predicted values into multiple intervals, and determining the probability distribution of the multiple groups of error values in the multiple intervals; and S5, predicting the data to be detected by using an artificial neural network model, and obtaining an audible noise probability prediction result according to the prediction result and the difference probability distribution of the interval where the prediction result is located.
Description
Technical Field
The invention belongs to the field of electrical engineering, and particularly relates to a method and a system for predicting audible noise probability of a direct-current transmission line.
Background
In recent years, the electromagnetic environment problem of high-voltage transmission lines is receiving public attention. The electromagnetic environment problem of the transmission line is mainly caused by corona discharge of the high-voltage transmission line, the corona discharge is a discharge form in an extremely uneven field, the curvature radius of the transmission line is small, in addition, certain burrs and defects often exist on the surface of a lead, so that the unevenness of an electric field near the surface of the lead of the high-voltage transmission line is very high, and the corona discharge can occur when the voltage of the lead reaches a certain degree. Electromagnetic environment problems such as radio interference, audible noise and the like can be generated in the corona discharge process, and the problems become key technical problems of high-voltage power transmission at present.
The audible noise generated by the corona of the power transmission line has a wide frequency band and is represented by disordered irregular noise, and compared with the noise generated by the common noise corona, the audible noise has a larger influence on a human body and seriously influences the normal work and life of people nearby the high-voltage line. Therefore, China has established relevant standards aiming at the problem of audible noise of the power transmission line. For example, the standard DL/T1088 of ± 800kV dc transmission line specifies that the value of audible noise 50% generated by corona when positive polarity wire is projected to ground on 20m clear days should not exceed 45db (a), and in addition, both the design of transmission line and the type selection of wire need to satisfy the relevant standards. In order to enable the audible noise level around the newly-built line to meet the requirements of relevant standards, the audible noise generated by the line needs to be predicted in the process of designing the line, and an accurate audible noise prediction formula is crucial in the design of the power transmission line. A plurality of research organizations at home and abroad fit respective empirical formulas according to the audible noise measurement result of the power transmission line, but the fitting formulas are obtained under respective specific conditions, and the application range of the fitting formulas is very limited. Therefore, the more accurate prediction method aiming at the audible noise of the direct current transmission line has more important significance to direct current line engineering.
Disclosure of Invention
In view of the above problems, the present invention provides a method for predicting audible noise probability of a dc power transmission line, the method comprising the steps of: s1, training an artificial neural network model by utilizing a plurality of groups of training data, wherein each group of training data at least comprises a line parameter and an audible noise measured value, in the training process, the line parameter is used as the input data of the artificial neural network model, and the audible noise measured value is used as the output data of the artificial neural network model; s2, inputting the circuit parameters in the multiple groups of training data into the trained artificial neural network model again, and correspondingly obtaining multiple groups of audible noise predicted values; s3, calculating error values of a plurality of groups of corresponding artificial neural network models according to the plurality of groups of audible noise measured values and the plurality of groups of audible noise predicted values; s4, dividing the multiple groups of audible noise predicted values into multiple intervals, and determining the probability distribution of the multiple groups of error values in the multiple intervals; s5, the artificial neural network model is used for predicting the data to be tested to obtain a prediction result, the interval where the prediction result is located is determined, and the audible noise probability prediction result is obtained according to the prediction result and the difference probability distribution of the interval where the prediction result is located.
Optionally, in step S3, the expression of the error value is:
ei＝Yi-yi
where i is 1 … n, n is the number of sets of training data, and Y isiRepresenting the audible noise prediction value, y, corresponding to the ith set of training dataiRepresenting an audible noise measurement in the ith set of training data.
Optionally, in the step S4, the multiple sets of audible noise prediction values are divided into k intervals, and if an error value corresponding to any one interval is arranged from small to large as { e1，e2...exAnd then, the probability distribution of the multiple sets of error values in the k intervals is:
wherein the content of the first and second substances,
to be located in a section
The number of error values in, x is the total number of error values, and e represents the prediction error variable.
Optionally, in step S5, the expression of the audible noise probability prediction result is:
t+Pt，
wherein t is a prediction result output by the artificial neural network model, PtIs the probability distribution of the error value of the interval where the predicted result t is located.
Optionally, the line parameters include at least one or more of line structure data, operating condition data, and meteorological data.
The invention provides a system for predicting the audible noise probability of a direct current transmission line, which comprises the following steps:
the training module is used for training an artificial neural network model by utilizing a plurality of groups of training data, wherein each group of training data at least comprises a line parameter and an audible noise measured value, in the training process, the line parameter is used as input data of the artificial neural network model, and the audible noise measured value is used as output data of the artificial neural network model;
the noise prediction module is used for inputting the line parameters in the multiple groups of training data into the trained artificial neural network model again to correspondingly obtain multiple groups of audible noise prediction values;
the error calculation module is used for calculating the error values of the artificial neural network models corresponding to the groups according to the groups of audible noise measured values and the groups of audible noise predicted values;
the probability distribution calculation module is used for dividing the multiple groups of audible noise predicted values into multiple intervals and determining the probability distribution of the multiple groups of error values in the multiple intervals;
and the noise probability prediction module is used for predicting the data to be tested by using the artificial neural network model to obtain a prediction result, determining the interval where the prediction result is located, and obtaining an audible noise probability prediction result according to the prediction result and the difference probability distribution of the interval where the prediction result is located.
Optionally, in the error calculation module, the expression of the error value is:
ei＝Yi-yi
where i is 1 … n, n is the number of sets of training data, and Y isiRepresenting the audible noise prediction value, y, corresponding to the ith set of training dataiRepresenting an audible noise measurement in the ith set of training data.
Optionally, in the probability distribution calculation module, the multiple sets of audible noise prediction values are divided into k intervals, and if an error value corresponding to any one interval is arranged from small to large as { e1，e2...exAnd then, the probability distribution of the multiple sets of error values in the k intervals is:
wherein the content of the first and second substances,
to be located in a section
The number of error values in, x is the total number of error values, and e represents the prediction error variable.
Optionally, in the noise probability prediction module, the expression of the audible noise probability prediction result is:
t+Pt，
wherein t is a prediction result output by the artificial neural network model, PtFor the prediction junctionProbability distribution of error values in the interval of the effect t.
Optionally, the line parameters include at least one or more of line structure data, operating condition data, and meteorological data.
The invention has the following beneficial effects:
(1) audible noise and line structure parameters, operation conditions and meteorological parameters are comprehensively considered, and dependent variables are considered more comprehensively;
(2) fitting the nonlinear relation between audible noise and other parameters by using a neural network model, so that the prediction result is more accurate;
(3) the prediction result of the probability distribution contains richer prediction information, and the interval where the prediction value is located can be better evaluated, so that the prediction result is more reliable.
Drawings
Fig. 1 is a flowchart of a method for predicting audible noise probability of a dc power transmission line according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a BP neural network in the embodiment of the present invention.
FIG. 3 is a diagram illustrating an embodiment of calculating an error value.
FIG. 4 is a diagram illustrating calculation of an audible noise probability prediction result according to an embodiment of the present invention.
Fig. 5 is a functional block diagram of an audible noise probability prediction system of a dc power transmission line according to an embodiment of the present invention.
Detailed Description
The invention provides a method and a system for predicting audible noise probability of a direct current transmission line, wherein the method comprises the following steps: s1, training the artificial neural network model by using multiple groups of training data, wherein in the training process, the line parameters are used as input data, and the audible noise measurement value is used as output data; s2, inputting the circuit parameters in the multiple groups of training data into the trained artificial neural network model again, and correspondingly obtaining multiple groups of audible noise predicted values; s3, calculating error values of a plurality of groups of corresponding artificial neural network models according to the plurality of groups of audible noise measured values and the plurality of groups of audible noise predicted values; s4, dividing the multiple groups of audible noise predicted values into multiple intervals, and determining the probability distribution of the multiple groups of error values in the multiple intervals; and S5, predicting the data to be detected by using an artificial neural network model, and obtaining an audible noise probability prediction result according to the prediction result and the difference probability distribution of the interval where the prediction result is located.
Other aspects, advantages and salient features of the invention will become apparent to those skilled in the art from the following detailed description, which, taken in conjunction with the annexed drawings, discloses exemplary embodiments of the invention.
In the present invention, the terms "include" and "comprise," as well as derivatives thereof, mean inclusion without limitation; the term "or" is inclusive, meaning and/or.
In this specification, the various embodiments described below which are meant to illustrate the principles of this invention are illustrative only and should not be construed in any way to limit the scope of the invention. The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of exemplary embodiments of the invention as defined by the claims and their equivalents. The following description includes various specific details to aid understanding, but such details are to be regarded as illustrative only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Moreover, descriptions of well-known functions and constructions are omitted for clarity and conciseness. Moreover, throughout the drawings, the same reference numerals are used for similar functions and operations.
Fig. 1 is a flowchart of a method for predicting audible noise probability of a dc power transmission line according to an embodiment of the present invention, where as shown in fig. 1, the method includes:
and S1, training the artificial neural network model by using multiple groups of training data, wherein each group of training data at least comprises line parameters and audible noise measured values, and in the training process, the line parameters are used as input data of the artificial neural network model, and the audible noise measured values are used as output data of the artificial neural network model.
In step S1, the line parameters of the present embodiment may at least include one or more of line structure data, operation condition data, and meteorological data; the line structure data may be a pole pitch of the power transmission line, a ground height of the power transmission line, a radius of the power transmission line, etc., the operation condition data may be an operation voltage, a current, etc., of the power transmission line, and the weather data may be a temperature, a humidity, etc., of surroundings of the power transmission line. The audible noise measurement value is the noise value actually measured when the power transmission line is in the line parameter, so that the line parameter and the audible noise measurement value are in one-to-one correspondence in a group of training data and can be used as input data and output data for training an artificial neural network model. In addition, in the embodiment, a large amount of training data (the number of groups can reach hundreds of thousands or more) is adopted when the artificial neural network model is trained.
Fig. 2 is a schematic structural diagram of a BP neural network according to an embodiment of the present invention, and as shown in fig. 2, the neural network includes an input layer, a hidden layer, and an output layer. X in FIG. 21，x2，…，xnIs the input value of the BP neural network, y1，y2，…，ymIs a predicted value, ω, of the BP neural networkijAnd ωjkIs the weight of the BP neural network. The artificial neural network is a multilayer feedforward neural network, the relation between input and output is established through operation of neuron nodes, the parameters of the neuron nodes are adjusted through the error between the output and an actual value, and finally a network structure with minimized error is established.
And S2, inputting the line parameters in the multiple groups of training data into the trained artificial neural network model again, and correspondingly obtaining multiple groups of audible noise predicted values.
Fig. 3 is a schematic diagram of calculating an error value according to an embodiment of the present invention, and as shown in fig. 3, after a neural network model is trained by using line data and an audible noise measurement value, line parameters are input into the trained artificial neural network model again. In step S2, the neural network model is a comprehensive result obtained by training a plurality of sets of training data, and when the neural network model is inputted to the neural network model again for each set of line data, the neural network model does not always output data that is the same as the audible noise measurement value, but data that deviates from the audible noise measurement value by a certain amount, and is referred to herein as an audible noise prediction value.
And S3, calculating error values of the artificial neural network models corresponding to the groups according to the groups of audible noise measured values and the groups of audible noise predicted values.
For the same set of line data, the line data corresponds to the audible noise measurement value in the training data and also corresponds to the audible noise prediction value output by the neural network model, specifically, in step S3, the audible noise measurement value and the audible noise prediction value are subtracted to obtain a corresponding error value, that is, the expression of the error value is:
ei＝Yi-yi
where i is 1 … n, n is the number of sets of training data, and Y isiRepresenting the audible noise prediction value, y, corresponding to the ith set of training dataiRepresenting an audible noise measurement in the ith set of training data.
And S4, dividing the multiple groups of audible noise predicted values into multiple intervals, and determining the probability distribution of the multiple groups of error values in the multiple intervals.
In step S4, the multiple sets of audible noise prediction values are divided into k sections, and the error values corresponding to any one section are arranged from small to large as { e }1，e2...exAnd then, the probability distribution of the multiple sets of error values in the k intervals is:
wherein the content of the first and second substances,
to be located in a section
The number of error values in, x is the total number of error values, and e represents the prediction error variable.
For example, there are 10 sets of audible noise prediction values, 10, 12, 15, 21, 29, 35, 56, 58, 78, and 80 (unit is dB), and the 10 sets of data are divided into 4 sections a, b, c, and d, where a: 0-25, b: 26-50, c: 51-75, d: 76-100, wherein the error values of the 10 groups are calculated by the formula, and the error values are shown in the following table in 4 intervals:
| interval(s) | Audible noise prediction | Corresponding error value |
| a：0～25 | 10、12、15 | 1、2、1 |
| b:26～50 | 21、29、35 | 2、2、-1 |
| c：51～75 | 56、58 | -1、4 |
| d：76～100 | 78、80 | -2、4 |
TABLE 1
As can be seen from the above table, in the interval a, the probability distribution of the error value 1 is 66.6%, and the probability distribution of the error value 2 is 33.3%, in the interval b, the probability distribution of the error value 2 is 66.6%, and the probability distribution of the error value-1 is 33.3%, in the interval c, the probability distribution of the error value-1 is 50%, and the probability distribution of the error value 4 is 50%, in the interval d, the probability distribution of the error value-2 is 50%, and the probability distribution of the error value 4 is 50%.
S5, predicting the data to be tested by using the artificial neural network model to obtain a prediction result, determining the interval of the prediction result, and obtaining an audible noise probability prediction result according to the difference probability distribution of the prediction result and the interval of the prediction result.
Fig. 4 is a schematic diagram illustrating calculation of an audible noise probability prediction result in an embodiment of the present invention, as shown in fig. 4, for a set of data to be tested, the data type of the data to be tested is consistent with the data type of the line data, and the data to be tested needs to be input into the artificial neural network, and a prediction result corresponding to the data to be tested is output, where the prediction result is a specific audible noise value. In step S5, the difference probability distribution of the section where the prediction result is located is obtained, and then the difference probability distribution is added to the prediction result to obtain the audible noise probability prediction result, where the expression is:
t+Pt，
wherein t is a prediction result output by the artificial neural network model, PtIs the probability distribution of the error value of the interval where the predicted result t is located.
For example, if the output prediction is 49dB, which falls within the interval b, the addition of the output prediction to the prediction of 49dB indicates that the audible noise probability prediction is 50dB (49 plus 1) at 66.6% and 51dB (49 plus 2) at 33.3%.
Fig. 5 is a functional block diagram of an audible noise probability prediction system of a dc power transmission line according to an embodiment of the present invention, and as shown in fig. 5, the system 500 includes a training module 510, a noise prediction module 520, an error calculation module 530, a probability distribution calculation module 540, and a noise probability prediction module 550. The system 400 may perform the methods described above with reference to fig. 1-4 to achieve audible noise probability prediction for a dc transmission line.
Specifically, the training module 510 is configured to train an artificial neural network model by using multiple sets of training data, where each set of training data at least includes a line parameter and an audible noise measurement value, and in the training process, the line parameter is used as input data of the artificial neural network model, and the audible noise measurement value is used as output data of the artificial neural network model; the noise prediction module 520 is configured to input the line parameters in the multiple sets of training data to the trained artificial neural network model again, and obtain multiple sets of audible noise prediction values correspondingly; the error calculation module 530 is configured to calculate error values of the multiple sets of corresponding artificial neural network models according to the multiple sets of audible noise measurement values and the multiple sets of audible noise prediction values; the probability distribution calculation module 540 is configured to divide the multiple sets of audible noise prediction values into multiple intervals, and determine probability distributions of the multiple sets of error values in the multiple intervals; the noise probability prediction module 550 is configured to predict data to be detected by using the artificial neural network model to obtain a prediction result, determine an interval where the prediction result is located, and obtain an audible noise probability prediction result according to the prediction result and a difference probability distribution of the interval where the prediction result is located. According to the embodiment of the present invention, the functional implementation of each module can be referred to the description above with reference to fig. 1 to 4, and is not repeated here.
The above-described methods, apparatuses, units and/or modules according to embodiments of the present invention may be implemented by an electronic device having computer capabilities executing software containing computer instructions. The system may include storage devices to implement the various storage described above. The computing-capable electronic device may include, but is not limited to, a general-purpose processor, a digital signal processor, a special-purpose processor, a reconfigurable processor, and the like capable of executing computer instructions. Execution of such instructions causes the electronic device to be configured to perform the operations described above in accordance with the present invention. The above devices and/or modules may be implemented in one electronic device, or may be implemented in different electronic devices. Such software may be stored in a computer readable storage medium. The computer readable storage medium stores one or more programs (software modules) comprising instructions which, when executed by one or more processors in the electronic device, cause the electronic device to perform the methods of the present invention.
Such software may be stored in the form of volatile memory or non-volatile storage (such as storage devices like ROM), whether erasable or rewritable, or in the form of memory (e.g. RAM, memory chips, devices or integrated circuits), or on optically or magnetically readable media (such as CD, DVD, magnetic disks or tapes, etc.). It should be appreciated that the storage devices and storage media are embodiments of machine-readable storage suitable for storing one or more programs that include instructions, which when executed, implement embodiments of the present invention. Embodiments provide a program and a machine-readable storage device storing such a program, the program comprising code for implementing an apparatus or method as claimed in any one of the claims of the invention. Further, these programs may be delivered electronically via any medium (e.g., communication signals carried via a wired connection or a wireless connection), and embodiments suitably include these programs.
Methods, apparatus, units and/or modules according to embodiments of the invention may also be implemented using hardware or firmware, for example Field Programmable Gate Arrays (FPGAs), Programmable Logic Arrays (PLAs), system on a chip, system on a substrate, system on a package, Application Specific Integrated Circuits (ASICs) or in any other reasonable manner for integrating or packaging circuits, or in any suitable combination of software, hardware and firmware implementations. The system may include a storage device to implement the storage described above. When implemented in these manners, the software, hardware, and/or firmware used is programmed or designed to perform the corresponding above-described methods, steps, and/or functions according to the present invention. One skilled in the art can implement one or more of these systems and modules, or one or more portions thereof, using different implementations as appropriate to the actual needs. All of these implementations fall within the scope of the present invention.
As will be understood by those skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations of subranges thereof. Any listed range can be easily identified as a sufficient description and enabling the same range to be at least broken down into equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each range discussed in this application can be readily broken down into a lower third, a middle third, and an upper third, among others. As those skilled in the art will also appreciate, all language such as "up to," "at least," "greater than," "less than," or the like, includes the recited quantity and refers to a range that can be subsequently broken down into subranges as discussed above. Finally, as will be understood by those skilled in the art, a range includes each individual component. So, for example, a group having 1-3 cells refers to a group having 1, 2, or 3 cells. Similarly, a group having 1-5 cells refers to groups having 1, 2, 3, 4, or 5 cells, and so forth.
While the invention has been shown and described with reference to certain exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents. Accordingly, the scope of the present invention should not be limited to the above-described embodiments, but should be defined not only by the appended claims, but also by equivalents thereof.
Claims (6)
1. A method for predicting audible noise probability of a direct current transmission line is characterized by comprising the following steps:
s1, training an artificial neural network model by utilizing a plurality of groups of training data, wherein each group of training data at least comprises a line parameter and an audible noise measured value, and in the training process, the line parameter is used as the input data of the artificial neural network model, and the audible noise measured value is used as the input data of the artificial neural network model;
s2, inputting the circuit parameters in the multiple groups of training data into the trained artificial neural network model again, and correspondingly obtaining multiple groups of audible noise predicted values;
s3, calculating error values of a plurality of groups of corresponding artificial neural network models according to the plurality of groups of audible noise measured values and the plurality of groups of audible noise predicted values;
s4, dividing the multiple sets of audible noise prediction values into multiple intervals, and determining the probability distribution of the multiple sets of error values in the multiple intervals, wherein in step S4, the multiple sets of audible noise prediction values are divided into k intervals, and if the error values corresponding to any one interval are arranged from small to large as { e }1，e2...exAnd then, the probability distribution of the multiple sets of error values in the k intervals is:
wherein the content of the first and second substances,
to be located in a section
The number of error values in the error model, x is the total number of error values, and e represents a prediction error variable;
s5, predicting the data to be tested by using the artificial neural network model to obtain a prediction result, determining the interval where the prediction result is located, and obtaining an audible noise probability prediction result according to the prediction result and the difference probability distribution of the interval where the prediction result is located, wherein in the step S5, the expression of the audible noise probability prediction result is as follows:
t+Pt，
wherein t is a prediction result output by the artificial neural network model, PtIs the probability distribution of the error value of the interval where the predicted result t is located.
2. The method for predicting the probability of the audible noise in the direct current transmission line according to claim 1, wherein in the step S3, the expression of the error value is as follows:
ei＝Yi-yi
where i is 1 … n, n is the number of sets of training data, and Y isiRepresenting the audible noise prediction value, y, corresponding to the ith set of training dataiRepresenting an audible noise measurement in the ith set of training data.
3. The method for predicting the probability of the audible noise of the direct current transmission line according to any one of claims 1 to 2, wherein the line parameters at least comprise one or more of line structure data, operation condition data and meteorological data.
4. A system for predicting the probability of audible noise of a direct current transmission line is characterized by comprising:
the training module is used for training an artificial neural network model by utilizing a plurality of groups of training data, wherein each group of training data at least comprises a line parameter and an audible noise measured value, in the training process, the line parameter is used as input data of the artificial neural network model, and the audible noise measured value is used as output data of the artificial neural network model;
the noise prediction module is used for inputting the line parameters in the multiple groups of training data into the trained artificial neural network model again to correspondingly obtain multiple groups of audible noise prediction values;
the error calculation module is used for calculating the error values of the artificial neural network models corresponding to the groups according to the groups of audible noise measured values and the groups of audible noise predicted values;
a probability distribution calculation module for dividing the multiple sets of audible noise predicted values into multiple intervals and determining the probability distribution of the multiple sets of error values in the multiple intervals, wherein the probability distribution calculation module divides the multiple sets of audible noise predicted valuesDividing the range into k ranges, and if the error value corresponding to any range is arranged from small to large as { e1，e2...exAnd then, the probability distribution of the multiple sets of error values in the k intervals is:
wherein the content of the first and second substances,
to be located in a section
The number of error values in the error model, x is the total number of error values, and e represents a prediction error variable;
the noise probability prediction module is used for predicting data to be tested by using the artificial neural network model to obtain a prediction result, determining an interval where the prediction result is located, and obtaining an audible noise probability prediction result according to the prediction result and the difference probability distribution of the interval where the prediction result is located, wherein in the noise probability prediction module, the expression of the audible noise probability prediction result is as follows:
t+Pt，
wherein t is a prediction result output by the artificial neural network model, PtIs the probability distribution of the error value of the interval where the predicted result t is located.
5. The system of claim 4, wherein in the error calculation module, the error value has an expression as follows:
ei＝Yi-yi
where i is 1 … n, n is the number of sets of training data, and Y isiRepresenting the audible noise prediction value, y, corresponding to the ith set of training dataiRepresenting an audible noise measurement in the ith set of training data.
6. The system of any one of claims 4 to 5, wherein the line parameters include at least one or more of line structure data, operating condition data, and meteorological data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710379112.6A CN107192898B (en) | 2017-05-25 | 2017-05-25 | Audible noise probability prediction method and system for direct current transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710379112.6A CN107192898B (en) | 2017-05-25 | 2017-05-25 | Audible noise probability prediction method and system for direct current transmission line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107192898A CN107192898A (en) | 2017-09-22 |
| CN107192898B true CN107192898B (en) | 2020-07-03 |
Family
ID=59875548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710379112.6A Active CN107192898B (en) | 2017-05-25 | 2017-05-25 | Audible noise probability prediction method and system for direct current transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107192898B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114034375B (en) * | 2021-10-26 | 2024-06-11 | 三峡大学 | Ultra-high voltage transmission line noise measurement system and method |
| CN115600076B (en) * | 2022-12-12 | 2023-05-02 | 中国南方电网有限责任公司超高压输电公司广州局 | Denoising model training method, device, computer equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101986358A (en) * | 2010-08-31 | 2011-03-16 | 彭浩明 | Neural network and fuzzy control fused electrical fire intelligent alarm method |
| CN103279804A (en) * | 2013-04-29 | 2013-09-04 | 清华大学 | Super short-period wind power prediction method |
| CN103986156A (en) * | 2014-05-14 | 2014-08-13 | 国家电网公司 | Dynamical probability load flow calculation method with consideration of wind power integration |
| CN104571262A (en) * | 2015-01-16 | 2015-04-29 | 江南大学 | Method for predicating interval probability of short-term wind power |
| CN104636801A (en) * | 2013-11-08 | 2015-05-20 | 国家电网公司 | Transmission line audible noise prediction method based on BP neural network optimization |
| CN105956682A (en) * | 2016-04-19 | 2016-09-21 | 上海电力学院 | Short-period electricity price prediction method based on BP neural network and Markov chain |
| CN106447103A (en) * | 2016-09-26 | 2017-02-22 | 河海大学 | Deep learning based QoS prediction method of Web service |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573980A (en) * | 2015-01-26 | 2015-04-29 | 国家电网公司 | Overhead power transmission line sag real-time estimation and pre-warning method |
-
2017
- 2017-05-25 CN CN201710379112.6A patent/CN107192898B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101986358A (en) * | 2010-08-31 | 2011-03-16 | 彭浩明 | Neural network and fuzzy control fused electrical fire intelligent alarm method |
| CN103279804A (en) * | 2013-04-29 | 2013-09-04 | 清华大学 | Super short-period wind power prediction method |
| CN104636801A (en) * | 2013-11-08 | 2015-05-20 | 国家电网公司 | Transmission line audible noise prediction method based on BP neural network optimization |
| CN103986156A (en) * | 2014-05-14 | 2014-08-13 | 国家电网公司 | Dynamical probability load flow calculation method with consideration of wind power integration |
| CN104571262A (en) * | 2015-01-16 | 2015-04-29 | 江南大学 | Method for predicating interval probability of short-term wind power |
| CN105956682A (en) * | 2016-04-19 | 2016-09-21 | 上海电力学院 | Short-period electricity price prediction method based on BP neural network and Markov chain |
| CN106447103A (en) * | 2016-09-26 | 2017-02-22 | 河海大学 | Deep learning based QoS prediction method of Web service |
Non-Patent Citations (1)
| Title |
|---|
| 风电功率短期预测及非参数区间估计;周松林 等;《中国电机工程学报》;20110905;第10-16页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107192898A (en) | 2017-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113937763B (en) | Wind power prediction method, device, equipment and storage medium | |
| EP3249769B1 (en) | System and method for controlling power production from a wind farm | |
| CN107192898B (en) | Audible noise probability prediction method and system for direct current transmission line | |
| CN103907034A (en) | Predicting the potential for severe weather | |
| CN106529732A (en) | Carbon emission efficiency prediction method based on neural network and random frontier analysis | |
| CN102436529B (en) | Modeling method for metal oxide semiconductor (MOS) transistor reliability statistics models distributed based on Weibull | |
| CN109598052B (en) | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis | |
| CN112491096A (en) | Method and system for generating power grid simulation analysis examples | |
| CN114065634A (en) | Data-driven power quality monitoring and stationing optimization method and device | |
| Yang et al. | Drought projection based on a hybrid drought index using Artificial Neural Networks | |
| CN107590570A (en) | A kind of bearing power Forecasting Methodology and system | |
| Zemzami et al. | Design flood estimation in ungauged catchments and statistical characterization using principal components analysis: application of Gradex method in Upper Moulouya | |
| CN113988398A (en) | Wind turbine generator power prediction method and device, electronic equipment and storage medium | |
| CN116776073B (en) | Pollutant concentration evaluation method and device | |
| CN114154753A (en) | Load prediction method and system | |
| CN106575870B (en) | For determining system, method and apparatus and the visible computer readable medium of the parameter setting for electricity generation system | |
| CN117094119B (en) | Reservoir dispatching method and computer taking power generation, ecological flow and surface water temperature into consideration | |
| CN109190749A (en) | A kind of prediction technique and device for the intelligent electric meter service life | |
| CN105825317A (en) | DC distribution network reliability assessment method based on Bayesian network | |
| JP5556418B2 (en) | Power leveling control device, power leveling control method, and power leveling control program | |
| CN110969296B (en) | Electric heating load prediction method and device and terminal equipment | |
| CN107861082A (en) | A kind of calibration intervals of electronic metering equipment determine method and device | |
| Dilini et al. | Effective water management in the mahaweli reservoir system: Analyzing the inflow of the upmost reservoir | |
| CN115689067A (en) | Solar irradiance prediction method, device and storage medium | |
| CN115907158A (en) | Load prediction method, device and storage medium based on heuristic configuration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |